© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2161
    Prev
    Next
    INDEX
    Explanations

    this week or year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    人人
    -0.08
    pping
    -0.08
    è¡Ķ
    -0.08
    åĿļ
    -0.08
    æ·¡æ·¡
    -0.08
    ä¸Ģåı¥è¯Ŀ
    -0.08
    çijĽ
    -0.08
     pyt
    -0.08
    иÑĢÑĥем
    -0.08
    们
    -0.07
    POSITIVE LOGITS
    imes
    0.10
    Allocation
    0.10
    è¿Ļä¹Īå¤ļ
    0.09
    åıªä¸įè¿ĩ
    0.09
    æĥĩ
    0.09
    æĻĤåĢĻ
    0.09
    /if
    0.09
    æ¬łç¼º
    0.09
    åĩıèĤ¥
    0.08
    çĿĢä»ĸ
    0.08
    Activations Density 0.030%

    No Known Activations